Update how-ssd-works.ipynb

Author: Yongyao Jiang

guide/14-deep-learning/how-ssd-works.ipynb

@@ -49,7 +49,7 @@
    "metadata": {},
    "source": [
     "It's natural to think of building an object detection model on the top of an image classification model. Once we have a good image classifier, a simple way to detect objects is to slide a 'window' across the image and classify whether the image in that window (cropped out region of the image) is of the desired type. Sounds simple! Well, there are at least two problems: \n",
-    "- (1) How do you know the **size of the window** so that it always contains the object? Different types of objects (cat and vehicle). Even the same type of objects (e.g. sedan and truck) can be of varying sizes as well. \n",
+    "- (1) How do you know the **size of the window** so that it always contains the object? Different types of objects (palm tree and swimming pool), even the same type of objects (e.g. a smalle building and a large buidling) can be of varying sizes as well. \n",
     "- (2) **Aspect ratio** (the ratio of height to width of a bounding box). A lot of objects can be present in various shapes like a building footprint will have a different aspect ratio than a palm tree.\n",
     "\n",
     "To solve these problems, we would have to try out different sizes/shapes of sliding window, which is very computationally intensive, especially with deep neural network. \n",
@@ -201,7 +201,7 @@
    "toc_cell": false,
    "toc_position": {},
    "toc_section_display": true,
-   "toc_window_display": true
+   "toc_window_display": false
   }
  },
  "nbformat": 4,